© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1966
    Prev
    Next
    INDEX
    Explanations

    Affordable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToolStrip
    -0.61
    JspWriter
    -0.59
     kasarigan
    -0.58
    PageContext
    -0.55
    ｀)
    -0.53
     dust
    -0.52
    Dust
    -0.52
    fromLTRB
    -0.51
    }$_
    -0.51
    낸
    -0.51
    POSITIVE LOGITS
    CppMethod
    0.76
     Roskov
    0.60
    ագրություններ
    0.60
    enterOuterAlt
    0.57
     Paglinawan
    0.55
    ⓧ
    0.54
    CloseOperation
    0.52
    caman
    0.51
     ffilm
    0.49
     للمعارف
    0.49
    Activations Density 0.003%

    No Known Activations